Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model Gen Li Tsinghua Y uting Wei CMU Y uejie Chi CMU Y uantao Gu Tsinghua Y uxin Chen Princeton
–Neural Information Processing Systems
Despite a number of prior work tackling this problem, a complete picture of the trade-offs between sample complexity and statistical accuracy is yet to be determined.
Neural Information Processing Systems
Aug-22-2025, 00:28:34 GMT